torchMoji
torchMoji copied to clipboard
huggingface
😇A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc
``` """ Creates a vocabulary from a tsv file. """ import codecs import example_helper from torchmoji.create_vocab import VocabBuilder from torchmoji.word_generator import TweetWordGenerator with codecs.open('../../twitterdata/tweets.2016-09-01', 'rU', 'utf-8') as stream: wg =...
I am trying to train a new model using the torchmoji architecture. I am not loading the pre-trained weights in the code. In torchmoji_transfer function calling the TorchMoji class but...
When I used evaluate-method ‘weighted_f1’ it occured.
After training the torchMoji model on the SemEval emotion dataset, I got the following error during the evaluation to measure F1: /torchMoji-master/torchmoji/finetuning.py in find_f1_threshold(model, val_gen, test_gen, average) 178 f1_scores =...
I tried finetuning with SS-Youtube dataset on `examples/finetune_youtube_last`. but There are some minor errors in there :(... First. The loss are not decrease well about each epochs when finetune using...
``` class DeepMojiBatchSampler(object): """A Batch sampler that enables larger epochs on small datasets and has upsampling functionality. # Arguments: y_in: Labels of the dataset. batch_size: Batch size. epoch_size: Number of...
Hi, I got the "IndexError: too many indices for array" error while I was running the file finetune_semeval_class-avg_f1. Here is more details: torchMoji-master/torchmoji/finetuning.py in (.0) 522 523 model.eval() --> 524...
"verbose" argument is missing from the fit_model function definition in finetuning.py. This leads to some errors
So, how can I implement cuda version of LSTM, I found torch._cudnn_rnn cannot be reached..?
Metadata
Owner
Metadata
😇A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc